Hello,
I might be wrong, but I think it is in degree. Let's consider the
length of a degree of longitude at 38N in kilometers: ~88 km
Thus, 40d * 88km = 3520km
Hope this helps,
Pascal
On 5 February 2014 00:43, Alicia <alicia.dalongeville at cirad.fr>
wrote:> Dear R-help,
>
> I used the correlog function of pgirmess package to create a spatial
> correlogram for Moran's I.
> The function gives Moran's coefficient with a p value for each distance
> class. My question is what is the unit for the distance classes?
> Here is the outcome of the function:
>
> Moran I statistic
> dist.class coef p.value n
> [1,] 1.283804 -0.0127393244 0.62182018 3288
> [2,] 3.851412 -0.0070005170 0.53767024 5642
> [3,] 6.419020 -0.0020360457 0.41371395 6546
> [4,] 8.986627 0.0173943620 0.07212314 5814
> [5,] 11.554235 -0.0225794695 0.84271228 4918
> [6,] 14.121842 -0.0050324772 0.49452160 3372
> [7,] 16.689450 -0.0007194256 0.42712852 2232
> [8,] 19.257058 -0.0162570231 0.60272799 1242
> [9,] 21.824665 -0.0330641732 0.74239660 1208
> [10,] 24.392273 0.0602675483 0.09440368 508
> [11,] 26.959881 -0.0007420201 0.43708138 270
> [12,] 29.527488 0.0765320993 0.10876925 190
> [13,] 32.095096 -0.0046161786 0.44659399 142
> [14,] 34.662703 -0.0797066199 0.61910376 58
> [15,] 37.230311 -0.7840212074 0.99986700 28
> [16,] 39.797919 -0.7770962373 0.99839965 18
>
> I first thought the distance unit was kilometers but the dist.class are
only
> going until 40 and my data are taken from all around the Mediterranean sea
> (about 3700km long) so it cannot be right.
>
> In the correlog help it is said that "Distances are in the same unit
as the
> spatial coordinates" but I don't get what that means. I gave
spatial
> coordinates in decimal degree.
>
> It must be very simple but I was not able to find the answer anywhere.
>
> Thanks for your help,
> Cheers,
>
> Alicia
>
>
>
> --
> View this message in context:
http://r.789695.n4.nabble.com/correlog-function-in-pgirmess-package-tp4684706.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
--
Pascal Oettli
Project Scientist
JAMSTEC
Yokohama, Japan